Mercurial > repos > artbio > mircounts
diff mircounts.xml @ 0:da29af78a960 draft
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
| author | artbio |
|---|---|
| date | Mon, 24 Jul 2017 06:27:50 -0400 |
| parents | |
| children | cadc0f2c6b29 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mircounts.xml Mon Jul 24 06:27:50 2017 -0400 @@ -0,0 +1,209 @@ +<tool id="mircounts" name="miRcounts" version="0.9"> + <description> Counts miRNA alignments from small RNA sequence data</description> + <requirements> + <requirement type="package" version="1.2">bowtie</requirement> + <requirement type="package" version="1.4.1">samtools</requirement> + <requirement type="package" version="0.11.2.1">pysam</requirement> + <requirement type="package" version="1.3.2=r3.3.2_0">r-optparse</requirement> + <requirement type="package" version="0.20_34=r3.3.2_0">r-lattice</requirement> + </requirements> + <command detect_errors="exit_code"><![CDATA[ + ## To be refactored with guidelines in https://github.com/ARTbio/tools-artbio/issues/140 + wget ftp://mirbase.org/pub/mirbase/CURRENT/genomes/${genomeKey}.gff3 && ## download gff3 specified by the variable genomeKey + python '$__tool_directory__'/mature_mir_gff_translation.py --input ${genomeKey}.gff3 --output $gff3 && ## transcode the mature miR genome coordinates into coordinates relative to the corresponding "miRNA_primary_transcript". + wget ftp://mirbase.org/pub/mirbase/CURRENT/hairpin.fa.gz && + sh '$__tool_directory__'/format_fasta_hairpins.sh $genomeKey && + #if $cutadapt.cutoption == "yes": + python '$__tool_directory__'/yac.py --input $cutadapt.input + --output clipped_input.fastq + --output_format fastq + --adapter_to_clip $cutadapt.clip_source.clip_sequence + --min $cutadapt.min + --max $cutadapt.max + --Nmode $cutadapt.Nmode && + #else + ln -f -s '$cutadapt.clipped_input' clipped_input.fastq && + #end if + bowtie-build hairpin.fa hairpin && + bowtie -v $v -M 1 --best --strata --norc -p \${GALAXY_SLOTS:-4} --sam hairpin -q clipped_input.fastq 2>/dev/null | samtools sort -O bam -o '$output' && + samtools index $output && + python '$__tool_directory__'/mircounts.py -pm --alignment $output --gff $gff3 --quality_threshold 10 --pre_mirs $pre_mir_count_file --mirs $mir_count_file --lattice $coverage_dataframe; + #if $plotting.plottingOption == 'yes': + Rscript '$__tool_directory__'/coverage_plotting.R --dataframe $coverage_dataframe --type $plotting.display --output $latticePDF + #end if + ]]></command> + <inputs> + <conditional name="cutadapt"> + <param label="Remove adapter sequence before aligning" name="cutoption" type="select"> + <option value="no">no</option> + <option selected="True" value="yes">yes</option> + </param> + <when value="yes"> + <param format="fastq,fastqsanger" label="Source file" name="input" type="data" /> + <param label="min size" name="min" size="4" type="integer" value="15" help="Minimum size of accepted clipped reads" /> + <param label="max size" name="max" size="4" type="integer" value="36" help="Maximum size of accepted clipped reads"/> + <param label="Accept reads containing N?" name="Nmode" type="select"> + <option selected="True" value="accept">accept</option> + <option value="reject">reject</option> + </param> + <conditional name="clip_source"> + <param help="Built-in adapters or User-provided" label="Source" name="clip_source_list" type="select"> + <option selected="True" value="prebuilt">Use a built-in adapter (select from the list below)</option> + <option value="user">Use custom sequence</option> + </param> + <when value="prebuilt"> + <param help="if your adapter is not listed, input your own sequence" label="Select Adapter to clip" name="clip_sequence" type="select"> + <option value="TCGTATGCCGTCTTCTGCTTG">Solexa TCGTATGCCGTCTTCTGCTTG</option> + <option value="ATCTCGTATGCCGTCTTCTGCTT">Illumina ATCTCGTATGCCGTCTTCTGCTT</option> + <option selected="True" value="TGGAATTCTCGGGTGCCAAG">Illumina TruSeq TGGAATTCTCGGGTGCCAAG</option> + <option value="CTGTAGGCACCATCAATCGT">IdT CTGTAGGCACCATCAATCGT</option> + </param> + </when> + <when value="user"> + <param label="Enter your Sequence" name="clip_sequence" size="35" type="text" value="GAATCC" /> + </when> + </conditional> + </when> + <when value="no"> + <param label="Select fastq files to align" name="clipped_input" type="data" format="fastq,fastqsanger" help="Note that sequences reads must be clipped from their adapter" /> + </when> + </conditional> + <param name="genomeKey" type="select" label="Choose Organism"> + <options from_data_table="miRbase_GenomeKeys"> + <column name="name" index="1"/> + <column name="value" index="0"/> + </options> + </param> + <param help="command [ bowtie -v 0,1,2,3 -M 1 --best --strata --norc ] will be used. Specify a value for -v (number of mismatches allowed)" label="Number of mismatches allowed" name="v" type="select"> + <option value="0">0</option> + <option selected="true" value="1">1</option> + <option value="2">2</option> + <option value="3">3</option> + </param> + <conditional name="plotting"> + <param label="Additional miRNA charts" name="plottingOption" type="select"> + <option value="no">no</option> + <option value="yes" selected="True">yes</option> + </param> + <when value="yes"> + <param label="Display Coverage with absolute number of reads or relatively to the total number of read matching the gene or mir" name="display" type="select"> + <option selected="True" value="relative">Relative Coverage</option> + <option value="absolute">Absolute Coverage</option> + </param> + </when> + <when value="no"> + </when> + </conditional> + </inputs> + <outputs> + <data format="bam" label="BAM alignment" name="output" /> + <data format="gff3" label="GFF3 generated by miRCounts" name="gff3"/> + <data format="tabular" label="Pre-mir Counts" name="pre_mir_count_file" /> + <data format="tabular" label="Mir Counts" name="mir_count_file" /> + <data format="tabular" label="Coverage Table" name="coverage_dataframe"> + <filter>plotting['plottingOption'] == "yes"</filter> + </data> + <data format="pdf" label="Pre-mir coverage (${plotting.display})" name="latticePDF"> + <filter>plotting['plottingOption'] == "yes"</filter> + </data> + </outputs> + <tests> + <test> + <param name="cutoption" value="yes" /> + <param name="min" value="15"/> + <param name="max" value="25"/> + <param name="Nmode" value="reject"/> + <param name="clip_sequence" value="TCGTATGCCGTCTTCTGCTTG"/> + <param name="v" value="0"/> + <param name="genomeKey" value="dme"/> + <param name="input" value="input.unclipped.fastqsanger" ftype="fastqsanger"/> + <param name="plottingOption" value="no"/> + <output name="output" file="unclipped.out.bam" ftype="bam"/> + <output name="gff3" file="translated_dme.gff3" ftype="gff3"/> + <output name="pre_mir_count_file" file="pre_mirs_unclipped_count.tab"/> + <output name="mir_count_file" file="mirs_unclipped_count.tab"/> + </test> + <test> + <param name="cutoption" value="yes" /> + <param name="min" value="15"/> + <param name="max" value="25"/> + <param name="Nmode" value="reject"/> + <param name="clip_sequence" value="TCGTATGCCGTCTTCTGCTTG"/> + <param name="v" value="0"/> + <param name="genomeKey" value="dme"/> + <param name="input" value="input.unclipped.fastqsanger" ftype="fastqsanger"/> + <param name="plottingOption" value="yes"/> + <param name="display" value="relative"/> + <output name="output" file="unclipped.out.bam" ftype="bam"/> + <output name="gff3" file="translated_dme.gff3" ftype="gff3"/> + <output name="pre_mir_count_file" file="pre_mirs_unclipped_count.tab"/> + <output name="mir_count_file" file="mirs_unclipped_count.tab"/> + <output name="latticePDF" file="mir_unclipped_coverage.pdf" ftype="pdf"/> + <output name="coverage_dataframe" file="lattice_unclipped_dataframe.tab"/> + </test> + <test> + <param name="cutoption" value="no" /> + <param name="v" value="1"/> + <param name="genomeKey" value="dme"/> + <param name="clipped_input" value="input.clipped.fastqsanger" ftype="fastqsanger"/> + <param name="plottingOption" value="yes"/> + <param name="display" value="absolute"/> + <output name="output" file="clipped.out.bam" ftype="bam"/> + <output name="gff3" file="translated_dme.gff3" ftype="gff3"/> + <output name="pre_mir_count_file" file="pre_mirs_clipped_count.tab"/> + <output name="mir_count_file" file="mirs_clipped_count.tab"/> + <output name="latticePDF" file="mir_clipped_coverage.pdf" ftype="pdf"/> + <output name="coverage_dataframe" file="lattice_clipped_dataframe.tab"/> + </test> + </tests> + <help> + +**What it does** +Clip adapter (optional), align small RNA read to miRNA mirBase_ reference using bowtie and compute pre-mir and mir counts using the pysam python package. +Optionally, pre-mir read coverages can be plotted using the R lattice package. +This tool uses a species-specific GFF3 file generated from mirBase_ to guide the parsing of a bam file of small RNA alignments. + +.. _mirBase: ftp://mirbase.org/pub/mirbase/CURRENT/genomes/ + +------ + + +**Inputs** + +1. a fastq file of reads that may or may not clipped from their adapter sequence. The tool includes a clipping option if needed. + +2. select the appropriate organism from which reads originate + +3. Choose whether you wish or not to plot the pre-mir coverages +Coverage can be expressed in absolute number of reads covering the real coordinates of the pre-mir sequences, +or, in fraction of reads relative to the maximum coverage (set to 1) covering the coordinates of pre-mirs +expressed as a fraction of the length of the pre-mirs. + +------ + +**Outputs** + +1. a BAM alignment of input reads +2. a gff3 file generated by the tool to compute mature mir counts +3 a table of pre-mir Counts +4 a table of mature mir Counts + +Optional: +5. A table of pre-mir coverage +6. A pdf file with covererage plots + + </help> + <citations> + <citation type="doi">10.1093/bioinformatics/btp352</citation> + <citation type="doi">10.1186/gb-2009-10-3-r25</citation> + <citation type="bibtex">@Book{, + title = {Lattice: Multivariate Data Visualization with R}, + author = {Deepayan Sarkar}, + publisher = {Springer}, + address = {New York}, + year = {2008}, + note = {ISBN 978-0-387-75968-5}, + url = {http://lmdvr.r-forge.r-project.org}, + }</citation> + </citations> +</tool>